Cluster view stability based query execution for compute scale and cache preservation

Abstract

A distributed query processor in a server is configured for compute scale and cache preservation to enable efficient cluster usage for query processing. The query processor includes an operator analyzer and an operator scheduler. The operator analyzer determines a first operator, of a graph of operators representative of a user query, to have a first characteristic and assigns the first operator to a first node set of a plurality of node sets. The first node set is associated with the first characteristic. A second node set of the node sets is associated with a second characteristic different from the first characteristic. The operator scheduler is configured to cause the first operator to be executed in the assigned first node set to generate a first operator result, and a query result to be generated based at least on the first operator result.

What is claimed is: 
     
         1 . A system, comprising:
 a processor; and   a memory device that stores program code structured to cause the processor to:
 receive a query, 
 determine a first operator of the query, 
 assign, based on a first characteristic of the first operator, the first operator to a first node set of a plurality of node sets, a number of nodes in the first node set more stable than a number of nodes in a second node set of the plurality of node sets, and 
 cause:
 the first operator to be executed in the first node set, resulting in a first operator result, and 
 a query result to be generated based on the first operator result. 
 
   
     
     
         2 . The system of  claim 1 , wherein nodes of the first node set are configured to maintain a cache in an idle configuration. 
     
     
         3 . The system of  claim 2 , wherein nodes of the second node set are not configured to maintain a cache in an idle configuration. 
     
     
         4 . The system of  claim 1 , wherein the program code is further structured to cause the processor to:
 assign a second operator of the query to the second node set;   cause a number of nodes assigned to the second node set to increase based on the assignment of the second operator.   
     
     
         5 . The system of  claim 4 , wherein the program code is further structured to cause the processor to:
 cause the number of nodes assigned to the second node set to decrease subsequent to execution of the second operator.   
     
     
         6 . The system of  claim 4 , wherein the program code is further structured to cause the processor to:
 cause the second operator to be executed in the second node set, resulting in a second operator result;   cause the query result to be generated based on the first operator result and the second operator result; and   cause the number of nodes assigned to the second node set to decrease subsequent to generation of the query result.   
     
     
         7 . The system of  claim 1 , wherein the program code is further structured to cause the processor to:
 determine the first operator has the first characteristic, the first characteristic being a cache preservation characteristic.   
     
     
         8 . A method, comprising:
 receiving a query;   determining a first operator of the query;   assigning, based on a first characteristic of the first operator, the first operator to a first node set of a plurality of node sets, a number of nodes in the first node set less stable than a number of nodes in a second node set of the plurality of node sets; and   cause:
 the number of nodes in the first node set to increase, 
 the first operator to be executed in the first node set, resulting in a first operator result, 
 a query result to be generated based on the first operator result, and 
 the number of nodes in the first node set to decrease subsequent to generation of the query result. 
   
     
     
         9 . The method of  claim 8 , wherein the first operator is assigned to a first node of the first node set and the method further comprises:
 determining a second operator of the query has the first characteristic; and   assigning the second operator to a second node of the first node set.   
     
     
         10 . The method of  claim 9 , wherein said assigning the second operator to the second node comprises:
 increasing the number of nodes in the first node set to include the second node; and   assigning the second operator to the second node.   
     
     
         11 . The method of  claim 8 , wherein the first operator is assigned to a first node of the first node set and the method further comprises:
 determining a second operator of the query has the first characteristic;   determining a maximum growth cap of the first node set is reached; and   assigning the second operator to the first node of the first node set.   
     
     
         12 . The method of  claim 8 , further comprising:
 determining the first characteristic of the first operator indicates the first operator is a computationally intensive operator.   
     
     
         13 . The method of  claim 8 , further comprising:
 determining a first operator of the query;   assigning, based on a second characteristic of the second operator, the second operator to the second node set; and   causing:
 the second operator to be executed in the second node set, resulting in a second operator result, and 
 the query result to be generated based on the first operator result and the second operator result. 
   
     
     
         14 . A method, comprising:
 receiving a query;   determining a first operator of the query;   assigning, based on a first characteristic of the first operator, the first operator to a first node set of a plurality of node sets, a number of nodes in the first node set more stable than a number of nodes in a second node set of the plurality of node sets; and   causing:
 the first operator to be executed in the first node set, resulting in a first operator result, and 
 a query result to be generated based on the first operator result. 
   
     
     
         15 . The method of  claim 14 , wherein nodes of the first node set are configured to maintain a cache in an idle configuration. 
     
     
         16 . The method of  claim 15 , wherein nodes of the second node set are not configured to maintain a cache in an idle configuration. 
     
     
         17 . The method of  claim 14 , further comprising:
 assigning a second operator of the query to the second node set;   causing a number of nodes assigned to the second node set to increase based on the assignment of the second operator.   
     
     
         18 . The method of  claim 17 , further comprising:
 causing the number of nodes assigned to the second node set to decrease subsequent to execution of the second operator.   
     
     
         19 . The method of  claim 17 , further comprising:
 causing the second operator to be executed in the second node set, resulting in a second operator result;   causing the query result to be generated based on the first operator result and the second operator result; and   causing the number of nodes assigned to the second node set to decrease subsequent to generation of the query result.   
     
     
         20 . The method of  claim 14 , further comprising:
 determining the first operator has the first characteristic, the first characteristic being a cache preservation characteristic.